Commit History
-
Replace dynamic-range int8 with weight-only int8
Verified signatureSame change as efficientnet_b1 (merged earlier today): the shipped dynamic-range int8 degrades accuracy on this architecture, while weight-only int8 is near-lossless at the same size reduction. Measured against the torch float reference on real photos plus fixed random tensors at native resolution: dynamic min logit correlation 0.986 (top-1 2/6) vs weight-only 1.000 (top-1 6/6). The replacement file is quantized directly from this repository's published float32 file (litert quantize, recipe weight_only_wi8_afp32), so the weights are identical. The model card is updated in the same commit: the metric entries for the removed dynamic file are dropped and a short quantized-variant note with the measured numbers is added.1d39335
-
Upload efficientnet_b5_Google_Tensor_G5_apply_plugin.tflite with huggingface_hub
Verified signatureb318a79
-
Updated README.md (#2)
- Updated README.md (105de9ab7f84a87b2d5b5a3dadb5caf575553376) Co-authored-by: Akash Verma <akashvverma1995@users.noreply.huggingface.co>5b6c94a
-
Update README: Add model card metadata, ImageNet-1k metrics, and LiteRT usage example (#1)
- Update README: Add model card metadata, ImageNet-1k metrics, and LiteRT usage example (83fa02235b31fd54c84946db7112fc3a211e59aa) Co-authored-by: Akash Verma <akashvverma1995@users.noreply.huggingface.co>f6434c9
-
Upload README.md with huggingface_hub
Verified signatureb6e59f0 -
Upload README.md with huggingface_hub
Verified signatureb4f00f9 -
Upload README.md with huggingface_hub
Verified signatureb95082e -
Initial model upload
Verified signature3d189e7 -
initial commit
Verified signature8bd5847